Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1502. Min Range: -8.1502
Max Act: 8.1502. Min Act: -0.1700
Data Index: 4867211 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.7752. Min Act: -0.1700
Data Index: 2683524 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.7752. Min Act: -0.1700
Data Index: 3128046 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.7127. Min Act: -0.1700
Data Index: 5395781 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.7127. Min Act: -0.1700
Data Index: 4398631 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.7127. Min Act: -0.1700
Data Index: 4474007 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.6502. Min Act: -0.1700
Data Index: 6010378 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.6502. Min Act: -0.1700
Data Index: 1037979 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.6502. Min Act: -0.1700
Data Index: 2903190 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.5877. Min Act: -0.1700
Data Index: 80265 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.5564. Min Act: -0.1700
Data Index: 144796 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.4939. Min Act: -0.1700
Data Index: 7242657 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.4939. Min Act: -0.1700
Data Index: 1074948 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.4939. Min Act: -0.1700
Data Index: 4313794 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.4314. Min Act: -0.1700
Data Index: 4685005 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.4314. Min Act: -0.1700
Data Index: 3739999 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.4002. Min Act: -0.1700
Data Index: 7882473 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.3689. Min Act: -0.1700
Data Index: 7283903 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.4002. Min Act: -0.1700
Data Index: 5098047 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1502. Min Range: -8.1502
Max Act: 7.4002. Min Act: -0.1700
Data Index: 3547860 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19